Intelligent decision support system for plateau dam dangerous case protection
Through real-time monitoring and analysis of the intelligent decision support system, the problem of insufficient comprehensive analysis of dangerous information in the dam protection system is solved, real-time data collection and dangerous situation prediction of plateau dams is realized, and the safety and reliability of the dams are improved.
Patent Information
- Application Number
- CN202411067330.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-06
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure CN119068632A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of plateau dam danger protection, and in particular to an intelligent decision support system for plateau dam danger protection. Background Art
[0002] Due to their special geographical location, dams in plateau areas often face many dangerous situations, such as landslides, floods, mudslides, etc.
[0003] Traditional dam protection systems usually include basic functions such as water level monitoring, soil displacement monitoring, and soil moisture monitoring, but lack comprehensive analysis and judgment of dangerous information. Relying on manual direct judgment of basic functions cannot effectively respond to complex dangerous situations in a timely manner. Therefore, an intelligent decision support system is urgently needed to improve the safety and reliability of dams. Summary of the invention
[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.
[0005] In view of the above problems existing in the existing dam protection system, the present invention is proposed.
[0006] Therefore, the technical problem solved by the present invention is to solve the problem that the existing dam protection system lacks comprehensive analysis and judgment of dangerous situation information, and relies on manual direct judgment of basic functions to fail to respond to complex dangerous situations in a timely and effective manner.
[0007] To solve the above technical problems, the present invention provides the following technical solutions: an intelligent decision support system for dangerous situation protection of plateau dams, comprising the following components: a monitoring subsystem, which monitors various indicators of the dam at rated time intervals through the configured sensors and cameras, and obtains changes in various indicators of the dam within each rated time period; a data processing system, which is wirelessly connected to the monitoring subsystem, obtains changes in various indicators of the dam within each rated time period, constructs a state change reference model, inputs corresponding changes in various indicators, and outputs state change reference values; an intelligent analysis system, which is wirelessly connected to the data processing system, obtains the state change reference values within each rated time period, constructs a state change-time curve, extracts features from the state change-time curve, constructs a feature analysis model, inputs the extracted feature quantity, and outputs the feature analysis quantity; an alarm decision system, which is wirelessly connected to the intelligent analysis system, obtains the feature analysis quantity, compares the abnormal alarm threshold, and completes the alarm decision.
[0008] As a preferred solution of the intelligent decision support system for dangerous situation protection of plateau dams described in the present invention, the various indicators obtained by the monitoring subsystem specifically include: obtaining the water level index α at the center of the dam within the rated time period through a float-type water level gauge; obtaining the soil displacement index β between the two ends of the dam body within the rated time period through a differential inductive displacement meter; and obtaining the soil moisture index γ at the center of the dam within the rated time period through a soil moisture sensor.
[0009] As a preferred solution of the intelligent decision support system for dangerous situation protection of plateau dams described in the present invention, the rated time period is defined as 12 hours.
[0010] As a preferred solution of the intelligent decision support system for plateau dam danger protection described in the present invention, the state change reference model constructed is specifically:
[0011]
[0012] Among them, δ is the state change reference value, α 差 is the water level index change difference within the current rated time period, β 差 is the soil displacement index difference within the current rated time period, γ 差 is the soil moisture index difference in the current rated time period, 1.013, 1, 2.66 and 1.874 are adjustment constants, and dx is the integral operation.
[0013] As a preferred solution of the intelligent decision support system for dangerous situation protection of plateau dams described in the present invention, when constructing the state change-time curve, the state change reference value within each rated time period is selected as the vertical coordinate, and the corresponding rated time period back end time is selected as the horizontal coordinate. After obtaining each reference point, each point is connected with a smooth curve to form the state change-time curve.
[0014] As a preferred solution of the intelligent decision support system for plateau dam danger protection described in the present invention, when the state change-time curve is subjected to feature extraction, the extracted feature quantities include: the maximum value of the curve, the minimum value of the curve and the difference in floating parameters obtained at each reference point of the curve;
[0015] The formula for obtaining the floating parameter difference is specifically:
[0016]
[0017] Wherein, η is the floating parameter difference, δ1 is the state change reference value obtained in the first rated time period, δ m is the state change reference value obtained in the mth rated time period, K 大 is the maximum value of the curve, K小 is the minimum value of the curve, 1.65 is the adjustment constant, and dx is the integral operation.
[0018] As a preferred solution of the intelligent decision support system for plateau dam danger protection described in the present invention, the characteristic analysis model constructed is specifically:
[0019]
[0020] Where θ is the characteristic analysis quantity, K 大 is the maximum value of the curve, K 小 is the minimum value of the curve, η is the floating parameter difference, 1.23 is the adjustment constant, and dx is the integral operation.
[0021] As a preferred solution of the intelligent decision support system for plateau dam dangerous situation protection described in the present invention, the abnormal alarm threshold is set to 2.43 or 2.431 or 2.4313.
[0022] As a preferred solution of the intelligent decision support system for plateau dam danger protection described in the present invention, when the characteristic analysis quantity is higher than the abnormal alarm threshold, the alarm decision system (400) makes an alarm decision.
[0023] The present invention provides an intelligent decision support system for plateau dam danger protection, which has the following beneficial effects:
[0024] 1. The intelligent decision support system for plateau dam danger protection of the present invention can collect and analyze relevant data of plateau dams in real time, thereby improving the accuracy and real-time performance of the data.
[0025] 2. The data processing system and intelligent analysis system of the present invention adopt machine learning and intelligent algorithms to establish a plateau dam hazard prediction model, which can accurately predict the occurrence and development trend of dam hazards.
[0026] 3. The decision output module of the present invention can generate corresponding protective measures and emergency plans according to the prediction results, providing a decision-making basis for relevant personnel.
[0027] 4. The present invention can realize the automatic operation and intelligent decision support of the system, and improve the reliability and stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:
[0029] Figure 1 The overall system module diagram of the intelligent decision support system for plateau dam dangerous situation protection provided by the present invention. DETAILED DESCRIPTION
[0030] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.
[0031] Traditional dam protection systems usually include basic functions such as water level monitoring, soil displacement monitoring, and soil moisture content monitoring, but lack comprehensive analysis and judgment of dangerous situation information. Relying on direct manual judgment of basic functions cannot respond to complex dangerous situations in a timely and effective manner.
[0032] Therefore, please refer to Figure 1 The present invention provides an intelligent decision support system for plateau dam danger protection, comprising the following components:
[0033] The monitoring subsystem 100 monitors various indicators of the dam at rated intervals through various sensors and cameras configured therein, and obtains changes in various indicators of the dam within each rated time period;
[0034] The data processing system 200 is wirelessly connected to the monitoring subsystem 100 to obtain the changes of various indicators of the dam in each rated time period, build a state change reference model, input the corresponding changes of various indicators, and output the state change reference value;
[0035] The intelligent analysis system 300 is wirelessly connected to the data processing system 200, obtains the reference value of the state change in each rated time period, constructs the state change-time curve, extracts the characteristics of the state change-time curve, constructs the characteristic analysis model, inputs the extracted characteristic quantity, and outputs the characteristic analysis quantity;
[0036] The alarm decision system 400 is wirelessly connected to the intelligent analysis system 300 to obtain characteristic analysis data, compare abnormal alarm thresholds, and complete alarm decisions.
[0037] Specifically, the indicators acquired by the monitoring subsystem 100 include:
[0038] ① Obtain the water level index α at the center of the dam within the rated time period through a float-type water level gauge;
[0039] It should be noted that a float-type water level gauge is a commonly used water level monitoring device that transmits water level information by the rise and fall of a float as the water level changes.
[0040] When measuring the water level index α, the following steps are included:
[0041] Installing a float water level gauge:
[0042] A float type water level gauge is installed at the center of the dam, which includes a float, a suspension cable, a counterweight, a water level wheel and an encoder.
[0043] A float is a device that floats on the water, usually made of lightweight material and marked with water level markings.
[0044] The catenary is a thin rope or chain that suspends the float, with one end connected to the float and the other end wrapped around the water level wheel.
[0045] The counterweight is a heavy object that balances the weight of the float, ensuring that the float pulls the suspension cable correctly as the water level changes.
[0046] The water level wheel is a wheel with a V-shaped groove and a suspension cable wrapped around it to record the number of times the water level changes.
[0047] The encoder is a device that converts the rotation of the water level wheel into a digital signal for accurate measurement of water level changes.
[0048] Measuring water level index α:
[0049] During the specified period of time, let the float float freely on the water surface and record the number of rotations of the water level wheel and the circumference of the water level wheel measurement circle.
[0050] An encoder is used to convert the number of rotations of the water level wheel into a digital signal of the water level height.
[0051] The height change of the water level during this period of time is calculated based on the measured circumference of the water level wheel and the number of rotations of the water level wheel.
[0052] The calculated water level height change value is used as the water level index α.
[0053] Repeat the measurement and record:
[0054] The above measurement and recording process is repeated in each specified time period to obtain multiple water level indicators α.
[0055] These water level indicators α will be used to analyze the water level change trend and hazard prediction of the dam.
[0056] ② Obtain the soil displacement index β between the two ends of the dam body within the rated time period through a differential inductive displacement meter;
[0057] It should be noted that a differential inductive displacement meter is a sensor commonly used to measure soil displacement. It determines the displacement by detecting the change in mutual inductance between two inductor coils.
[0058] When measuring the soil displacement index β, the following steps are included:
[0059] Installing a differential inductive displacement meter:
[0060] Two inductance coils are installed on both sides of the dam body, one as the main coil and the other as the secondary coil.
[0061] The primary and secondary coils are arranged at a certain distance to suit the shape and size of the dam.
[0062] Connect both coils to a differential amplifier, which can reject common-mode interference and amplify only the difference signal between the two coils.
[0063] Measuring soil displacement index β:
[0064] During the specified time period, the differential inductance displacement meter starts to work and mutual induction electromotive force is generated between the main coil and the secondary coil.
[0065] The magnitude of the mutual electromotive force is proportional to the relative displacement between the two coils.
[0066] The differential amplifier differentiates the electromotive force of the two coils, amplifies their difference signal, and converts it into a digital signal.
[0067] Based on the converted digital signal, the soil displacement between the two ends of the dam body is calculated.
[0068] The calculated soil displacement is taken as the soil displacement index β.
[0069] Repeat the measurement and record:
[0070] The above measurement and recording process is repeated in each specified time period to obtain multiple soil displacement indicators β.
[0071] These soil displacement indices β will be used to analyze the displacement change trend and hazard prediction of the dam.
[0072] ③ The soil moisture index γ at the center of the dam within the rated time period is obtained through the soil moisture sensor.
[0073] It should be noted that the soil moisture sensor is a device used to measure the moisture content of the soil. It can detect the moisture of the soil through different principles.
[0074] When measuring the soil moisture index γ, the following steps are included:
[0075] Installing the Soil Moisture Sensor:
[0076] Install a soil moisture sensor at the center of the embankment.
[0077] The soil moisture sensor can be a contact sensor or a non-contact sensor such as a frequency domain reflectometry (FDR) sensor or a time domain reflectometry (TDR) sensor.
[0078] The design of the sensor should be adapted to the soil type and environmental conditions of the dam.
[0079] Measuring soil moisture index γ:
[0080] During the specified period of time, the soil moisture sensor begins to work and measures the dielectric constant or conductivity of the soil.
[0081] The dielectric constant, or electrical conductivity, of soil is directly related to the moisture content of the soil.
[0082] Sensors convert the measured physical quantities into electrical signals, which can be read directly or recorded by data acquisition equipment.
[0083] Based on the measurement results of the sensor, the soil moisture content at the center of the dam is calculated.
[0084] The calculated soil moisture content is used as the soil moisture index γ.
[0085] Repeat the measurement and record:
[0086] Repeat the above measurement and recording process in each specified time period to obtain multiple soil moisture content indicators γ.
[0087] These soil moisture indexes γ will be used to analyze soil moisture variation trends and hazard prediction of dams.
[0088] Specifically, the rated time period is defined as 12 hours. Of course, the rated time in the present invention does not make a fixed time requirement, and can be adjusted accordingly according to actual conditions.
[0089] Furthermore, the constructed state change reference model is specifically as follows:
[0090]
[0091] Among them, δ is the reference value of state change, α 差 is the water level index change difference within the current rated time period, β 差 is the soil displacement index difference within the current rated time period, γ 差is the soil moisture index difference in the current rated time period, 1.013, 1, 2.66 and 1.874 are adjustment constants, and dx is the integral operation.
[0092] It should be noted that when using the above model, you first need to obtain the difference of each indicator within the rated time period. This is not difficult to understand. The indicator value obtained at the back-end time point within a rated time period is subtracted from the indicator value obtained at the front-end time point within the rated time period.
[0093] It should be noted that when confirming the above model, three basic influencing factors must be determined first: water level index change difference, soil displacement index difference and soil moisture index difference. The first three items of the model represent the individual influence of the basic influencing factors, and the fourth item of the main model expresses the dual influence of soil displacement index difference under soil moisture index difference, because in the actual prediction process, soil moisture index difference and soil displacement index difference are the core reference quantities for whether the dam body is solid, and then the influence is expanded and expressed in the form of integration.
[0094] Specifically, when constructing the state change-time curve, the state change reference value within each rated time period is selected as the ordinate, and the corresponding rated time period back end time is selected as the abscissa. After obtaining each reference point, each point is connected with a smooth curve to form a state change-time curve.
[0095] Furthermore, when extracting features from the state change-time curve, the extracted features include: the maximum value of the curve, the minimum value of the curve, and the difference in floating parameters obtained from each reference point of the curve;
[0096] Among them, the formula for obtaining the floating parameter difference is as follows:
[0097]
[0098] Among them, η is the floating parameter difference, δ1 is the state change reference value obtained in the first rated time period, δ m is the state change reference value obtained in the mth rated time period, K 大 is the maximum value of the curve, K 小 is the minimum value of the curve, 1.65 is the adjustment constant, and dx is the integral operation.
[0099] It should be noted that in the above model, the model for obtaining the difference of floating parameters needs to be explained. The first term in the model formula reflects the degree of difference between reference points through norm expression. The second term of the model obtains the degree of difference between the maximum and minimum values of the curve, and expands the degree of difference through integral expression.
[0100] Furthermore, the constructed feature analysis model is as follows:
[0101]
[0102] Among them, θ is the characteristic analysis quantity, K 大 is the maximum value of the curve, K 小 is the minimum value of the curve, η is the floating parameter difference, 1.23 is the adjustment constant, and dx is the integral operation.
[0103] Specifically, the abnormal alarm threshold is set to 2.43 or 2.431 or 2.4313.
[0104] Specifically, when the characteristic analysis value is higher than the abnormal alarm threshold, the alarm decision system 400 makes an alarm decision.
[0105] In order to prove the effectiveness of the intelligent decision support system for plateau dam danger protection of the present invention, the following proof experiments are carried out:
[0106] Purpose of the experiment: To verify the effectiveness of real-time data collection, data processing, hazard prediction and decision output of the intelligent decision support system for dam hazard protection on the plateau.
[0107] Experimental Materials:
[0108] 1. Intelligent decision support system for dangerous situation protection of plateau embankments.
[0109] 2. Weather station equipment.
[0110] 3. Water level monitoring equipment.
[0111] 4. Geological monitoring equipment.
[0112] 5. Soil moisture sensor.
[0113] 6. Data recording and analysis software.
[0114] Experimental equipment:
[0115] 1. Weather station: used to monitor meteorological data such as temperature, humidity, wind speed and precipitation.
[0116] 2. Water level monitoring equipment: used to monitor the water level of the dam in real time.
[0117] 3. Geological monitoring equipment: used to monitor soil displacement.
[0118] 4. Soil moisture sensor: used to measure soil moisture content.
[0119] 5. Data recording and analysis software: used to record experimental data and analyze results.
[0120] Experimental steps:
[0121] 1. Deploy meteorological stations, water level monitoring equipment, geological monitoring equipment and soil moisture sensors at the center of the dam and on both sides.
[0122] 2. Start the data recording and analysis software, ensure that all monitoring devices are properly connected to the system and start real-time data transmission.
[0123] 3. Collect meteorological, water level, geological and soil moisture data within a certain time range.
[0124] 4. Use intelligent decision support system to process and analyze the collected data and establish a dam hazard prediction model.
[0125] 5. Generate dam hazard warning and emergency plan based on the prediction model.
[0126] 6. Record the system’s decision outputs and implement the measures in the plan.
[0127] 7. Analyze the effects of implemented measures and evaluate the accuracy and reliability of the system.
[0128] Experimental data recording form:
[0129] Table 1: Experimental data record table
[0130] Data Types Data indicators Data Description Data Unit Data Value Weather data temperature Real-time temperature value ℃ 10 Weather data humidity Real-time humidity value % 60 Weather data Wind speed Real-time wind speed value m / s 5 Weather data Precipitation Real-time precipitation mm 10 Water level data Water level Real-time water level value m 5.0 Geological data Soil displacement Real-time displacement value mm 2 Soil data Water content Real-time moisture content % 25
[0131] Experimental data analysis:
[0132] 1. Meteorological data analysis:
[0133] Temperature: During the experiment, the temperature fluctuated between 10℃ and 15℃, with no extreme high or low temperatures, which had little impact on the stability of the dam.
[0134] Humidity: The humidity is maintained at around 60%, indicating that the air humidity is moderate and has no obvious erosion effect on the dam.
[0135] Wind speed: The wind speed is below 5m / s, and there is no water level fluctuation caused by strong wind, which is beneficial to the stability of the dam.
[0136] Precipitation: The precipitation is 10mm, which has little impact on the dam.
[0137] 2. Water level data analysis:
[0138] Water level: The water level fluctuates between 5m and 5.5m, with no obvious upward trend, and has no significant impact on the stability of the dam.
[0139] 3. Geological data analysis:
[0140] Soil displacement: The soil displacement is between 2mm and 15mm, and no significant displacement occurs, indicating that the soil stability is good.
[0141] 4. Soil data analysis:
[0142] Moisture content: The soil moisture content is around 25%, indicating that the soil is relatively dry, which is beneficial to the stability of the dam.
[0143] Experimental conclusion:
[0144] According to the analysis of experimental data, the intelligent decision support system for plateau dam danger protection of the present invention performs well in the following aspects:
[0145] 1. Real-time data collection: The system can accurately and timely collect meteorological, water level, geological and soil data of the dam.
[0146] 2. Data processing and analysis: The system processes and analyzes data through machine learning and intelligent algorithms, and effectively establishes a dam hazard prediction model.
[0147] 3. Danger prediction: The model can accurately predict the occurrence and development trend of dam hazards, providing a reliable basis for decision-making.
[0148] 4. Decision output: Based on the prediction results, the system generates reasonable protective measures and emergency plans, providing clear operational guidance for on-site personnel.
[0149] 5. System stability: The system's automated operation and intelligent decision-making support improve the reliability and stability of dam hazard protection.
[0150] The present invention provides an intelligent decision support system for plateau dam danger protection, which has the following beneficial effects:
[0151] 1. The intelligent decision support system for plateau dam danger protection of the present invention can collect and analyze relevant data of plateau dams in real time, thereby improving the accuracy and real-time performance of the data.
[0152] 2. The data processing system and intelligent analysis system of the present invention adopt machine learning and intelligent algorithms to establish a plateau dam hazard prediction model, which can accurately predict the occurrence and development trend of dam hazards.
[0153] 3. The decision output module of the present invention can generate corresponding protective measures and emergency plans according to the prediction results, providing a decision-making basis for relevant personnel.
[0154] 4. The present invention can realize the automatic operation and intelligent decision support of the system, and improve the reliability and stability of the system.
[0155] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. An intelligent decision support system for plateau dam danger protection, characterized in that: Includes the following components: The monitoring subsystem (100) monitors various indicators of the dam at rated intervals through various sensors and cameras configured therein, and obtains changes in various indicators of the dam within each rated time period; The data processing system (200) is wirelessly connected to the monitoring subsystem (100) to obtain the changes of various indicators of the dam in each rated time period, construct a state change reference model, input the corresponding changes of various indicators, and output a state change reference value; The intelligent analysis system (300) is wirelessly connected to the data processing system (200) to obtain the state change reference value in each rated time period, construct a state change-time curve, extract features from the state change-time curve, construct a feature analysis model, input the extracted feature quantity, and output the feature analysis quantity; The alarm decision system (400) is wirelessly connected to the intelligent analysis system (300) to obtain the characteristic analysis quantity, compare the abnormal alarm threshold value, and complete the alarm decision.
2. The intelligent decision support system for plateau dam danger protection according to claim 1 is characterized in that: The various indicators acquired by the monitoring subsystem (100) specifically include: The water level index α at the center of the dam within a rated time period is obtained by a float-type water level gauge; The soil displacement index β between the two ends of the dam body within the rated time period is obtained by using a differential inductive displacement meter; The soil moisture index γ at the center of the dam within a rated time period is obtained through a soil moisture sensor.
3. The intelligent decision support system for plateau dam danger protection according to claim 2 is characterized by: The rated time period is defined as 12 hours.
4. The intelligent decision support system for plateau dam danger protection according to claim 3 is characterized in that: The state change reference model constructed is specifically: Among them, δ is the state change reference value, α 差 is the water level index change difference within the current rated time period, β 差 is the soil displacement index difference within the current rated time period, γ 差 is the soil moisture index difference in the current rated time period, 1.013, 1, 2.66 and 1.874 are adjustment constants, and dx is the integral operation.
5. The intelligent decision support system for plateau dam danger protection according to claim 4 is characterized by: When constructing the state change-time curve, the state change reference value within each rated time period is selected as the ordinate, and the corresponding rated time period back end time is selected as the abscissa. After obtaining each reference point, each point is connected with a smooth curve to form the state change-time curve.
6. The intelligent decision support system for plateau dam danger protection according to claim 5 is characterized in that: When extracting features from the state change-time curve, the extracted features include: the maximum value of the curve, the minimum value of the curve, and the difference in floating parameters obtained from each reference point of the curve; The formula for obtaining the floating parameter difference is specifically: Wherein, η is the floating parameter difference, δ1 is the state change reference value obtained in the first rated time period, δ m is the state change reference value obtained in the mth rated time period, K 大 is the maximum value of the curve, K 小 is the minimum value of the curve, 1.65 is the adjustment constant, and dx is the integral operation.
7. The intelligent decision support system for plateau dam danger protection according to claim 6 is characterized in that: The feature analysis model constructed is specifically: Where θ is the characteristic analysis quantity, K 大 is the maximum value of the curve, K 小 is the minimum value of the curve, η is the floating parameter difference, 1.23 is the adjustment constant, and dx is the integral operation.
8. The intelligent decision support system for plateau dam danger protection according to claim 7 is characterized by: The abnormal alarm threshold is set to 2.43 or 2.431 or 2.4313.
9. The intelligent decision support system for plateau dam danger protection according to claim 8 is characterized by: When the characteristic analysis value is higher than the abnormal alarm threshold, the alarm decision system (400) makes an alarm decision.
Citation Information
Cited By
Motor control method and system for intelligent pool
CN119382573A
